© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35590
    Prev
    Next
    INDEX
    Explanations

    code structures

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on CamelCase code identifiers (e.g. class, namespace, type, and property names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cantora
    -1.10
    \
    -1.02
     blusa
    -1.01
     maleta
    -0.97
    FirebaseAuth
    -0.94
     hagan
    -0.94
     increment
    -0.91
     hice
    -0.91
    industries
    -0.91
     tumba
    -0.90
    POSITIVE LOGITS
    gründet
    1.11
     foglie
    1.05
    HomeAsUp
    1.03
     Indep
    1.02
    Aantal
    1.00
    tráfico
    1.00
     homicidio
    0.96
     odi
    0.96
     теперь
    0.95
     lumens
    0.95
    Activations Density 0.001%

    No Known Activations